Skip to main content

Biomechanics

QuickPose accelerates development of biomechanics for sporting and fitness applications.

shoulder-conditional-image
Bike Side View Video by Tariq Ali

This page describes a number of different techniques designed to simplify use for analysing sports footage;

Stacked Feature Styling​

To show multiple features you'll need to extend your quickpose call as described in the Getting Started Guide:

let bikeStyle = QuickPose.Style(relativeFontSize: 0.33, relativeArcSize: 0.4, relativeLineWidth: 0.3)
let feature1: QuickPose.Feature = .rangeOfMotion(.shoulder(side: .right, clockwiseDirection: false), style: bikeStyle)
let feature2: QuickPose.Feature = .rangeOfMotion(.elbow(side: .right, clockwiseDirection: false), style: bikeStyle)
let feature3: QuickPose.Feature = .rangeOfMotion(.hip(side: .right, clockwiseDirection: false), style: bikeStyle)
let feature4: QuickPose.Feature = .rangeOfMotion(.knee(side: .right, clockwiseDirection: true), style: bikeStyle)
let bikeFeatures = [feature1,  feature2, feature3, feature4]

quickPose.start(features: bikeFeatures, onFrame: { status, image, features, feedback, landmarks in
    switch status {
        case .success:
            overlayImage = image
            if let result = features.values.first  {
                feedbackText = result.stringValue
            } else {
                feedbackText = nil
            }
        case .noPersonFound:
            feedbackText = "Stand in view";
        case .sdkValidationError:
            feedbackText = "Be back soon";
    }
})

Increasing Framerate to 60fps​

For real time sports tracking we strongly reading our high performance guide, where we talk about raising frame rates to 60fps and above.

To process higher frame rates than the device can support in realtime, you can use QuickPose to post-process a pre-recorded video, and build a new output video at the desired framerate.

Lag-free Post Processing​

For analysing lag free, we suggest our post processing feature. By processing the frames after the event, all of your devices resources can be used to capture footage.

240 fps Slow Mo
Lag-free 240fps video rendering

Checkout our Post Processing Docs, but note this might not be applicable for all use cases, say where the user requires continuous feedback.

Using World Coordinates​

By default the coordinates generated by QuickPose describe the users location across the camera's image. For sports tracking we suggest using world coordinates, which renders the users coordinates more accurately in 3D, and converting them to be relative to the users hip. This basically means wherever the user is performing their activity will generate consisteny coordinates, whereas the default coordinates will mark people closer to the camera as larger.

To generate comparable coordinates for your users we recommend reading about our Extracting World Coordinates feature.

quickPose.start(features: [.showPoints()], onFrame: { status, image, features, feedback, landmarks in                
    switch status {
        case .success:
            overlayImage = image
            if let landmarks = landmarks {    
                let bodyNose = landmarks.worldLandmark(forBody: .nose)
                print(bodyNose)
            }
            ...
    }
})